CN108922191B - Travel time calculation method based on soft set - Google Patents

Travel time calculation method based on soft set Download PDF

Info

Publication number
CN108922191B
CN108922191B CN201810847570.2A CN201810847570A CN108922191B CN 108922191 B CN108922191 B CN 108922191B CN 201810847570 A CN201810847570 A CN 201810847570A CN 108922191 B CN108922191 B CN 108922191B
Authority
CN
China
Prior art keywords
road section
traffic
fuzzy
road
representing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810847570.2A
Other languages
Chinese (zh)
Other versions
CN108922191A (en
Inventor
李华民
王青青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University
Original Assignee
Chongqing University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing University filed Critical Chongqing University
Priority to CN201810847570.2A priority Critical patent/CN108922191B/en
Publication of CN108922191A publication Critical patent/CN108922191A/en
Application granted granted Critical
Publication of CN108922191B publication Critical patent/CN108922191B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a soft set-based travel time calculation method, which comprises the steps of establishing a traffic condition data table of a certain road section, wherein the table mainly comprises speed, flow, environmental weather, emergency and time factors; the mutual relation among all factors is solved to construct fuzzy approximationA space (U, R), wherein U represents a set of various factors affecting travel time, and R represents a fuzzy relationship between elements in U; fuzzy rough set of space (U, R) by fuzzy approximation
Figure DDA0001746942230000011
A fuzzy set I on a set U representing the traffic condition of the road section and used for setting the threshold value of the road section with the road conditioniTo represent a certain traffic state of the road section and then to find a fuzzy rough set
Figure DDA0001746942230000012
Constructing a soft fuzzy rough set; using a matching function to find
Figure DDA0001746942230000013
And

Description

Travel time calculation method based on soft set
Technical Field
The invention relates to a travel time estimation method, in particular to a travel time calculation method based on a soft set.
Background
The travel time on the urban road section mainly depends on the road technical conditions and the road traffic flow conditions, the conventional road section traffic cost prediction method mainly uses historical and real-time floating car data and traffic coil flow data as the basis and utilizes a traffic flow mechanism model and a statistical model to predict the vehicle passing section time, but the complexity of the road network causes that the travel time of the whole road section of the road network is difficult to predict on multiple scales, and a complete and feasible method is lacked. Firstly, the complexity of the road traffic network determines the relationship between the road section travel time and a plurality of influencing factors of the target road section, and the influencing factors with an undefined coupling relationship have a serious nonlinear relationship with the road section travel time. Secondly, a large number of block roads which mainly travel in a man-vehicle mixed behavior and lack traffic state information exist in the road network, and the road travel time which is consistent with the road network state is difficult to obtain only by taking the road self parameters as basic parameters for predicting the road travel time. Thirdly, under the constraint of traffic lights, the periodic starting and stopping of vehicles at the intersection makes the traffic state change at the intersection more complex, and meanwhile, the vehicle queuing length has great influence on the traffic time at the traffic intersection and is difficult to measure, which brings great difficulty to the prediction of the traffic time at the traffic intersection.
At the present stage, a plurality of models are used for predicting the travel time, but experimental results show that the fitting result is not good, some errors exist between the fitting result and the actual situation, and the fitting result is an exact result for predicting the travel time, but the travel time is difficult to accurately predict under various conditions of road traffic.
Disclosure of Invention
In view of the above, in order to solve the above problem, the present invention provides a method for calculating a travel time based on a soft set. Aiming at the uncertainty characteristic of the travel time, the method adopts a soft set method, establishes various soft fuzzy rough sets, considers some uncertainty problems, realizes effective estimation of the travel time, and better accords with the actual traffic condition.
In order to achieve the above objects and other objects, the present invention provides the following technical solutions: a travel time calculation method based on a soft set comprises the following steps:
establishing a traffic condition data table of a certain road section, wherein the table mainly comprises speed, flow, environmental weather, emergencies and time factors; solving the mutual relation among all factors, and constructing a fuzzy approximation space (U, R), wherein U represents a set formed by all factors influencing travel time, and R represents the fuzzy relation among elements in U;
fuzzy rough set of space (U, R) by fuzzy approximation
Figure GDA0002934759730000011
A fuzzy set I on a set U representing the traffic condition of the road section and used for setting the threshold value of the road section with the road conditioniTo represent a certain traffic state of the road section and then to find a fuzzy rough set
Figure GDA0002934759730000021
Constructing a soft fuzzy rough set;
solving by correlation matching function
Figure GDA0002934759730000022
And
Figure GDA0002934759730000023
then, according to the size of the correlation SIM (Q, Q), the traffic state of the road section is judged; and mapping to travel time according to the traffic state of the road.
Preferably, said fuzzy rough set
Figure GDA0002934759730000024
Is composed of
Figure GDA0002934759730000025
Wherein
Figure GDA0002934759730000026
Representing factor t for traffic state IiThe minimum value of the influence of (a) is,
Figure GDA0002934759730000027
representing the traffic state I of the factor t for the road sectioniMaximum value of the effect produced;
Figure GDA0002934759730000028
representing factor s in fuzzy set IiR (t, s) represents the fuzzy relationship between any two factors in U; threshold set I for congestioniAnd (3) an expectation of the degree of influence of various factors on the traffic state when a certain congestion state occurs on the road section.
Preferably, the constructing soft fuzzy rough set is as follows:
Figure GDA0002934759730000029
q(t) represents the minimum value of the influence of the factor t on the road section traffic state when the road section is in the instant condition;
Figure GDA00029347597300000210
the reason when the instant condition of the road section is shownAnd the maximum influence of the element t on the road section traffic state.
Wherein
Figure GDA00029347597300000211
μ(s) represents the fuzzy vector set on U, R (t)iS) represents the fuzzy relationship between any two factors in U; and by using the soft fuzzy rough set, according to the digital characteristics of the road section at a certain moment provided by the observer, the fuzzy rough set corresponding to the traffic condition observation value x of the road section at a certain moment is obtained.
Preferably, the correlation matching function is:
Figure GDA00029347597300000212
wherein Q and Q are fuzzy rough sets of traffic conditions and instantaneous conditions of the road segments respectively,
Figure GDA00029347597300000213
representing factor t for traffic state IiThe minimum value of the influence of (a) is,q(t) represents the minimum value of the influence of the factor t on the traffic state of the road section when the road section is in the instant condition, and Λ represents the sum of the values;
Figure GDA0002934759730000031
representing the traffic state I of the factor t for the road sectioniThe maximum value of the influence that is produced,
Figure GDA0002934759730000032
the maximum value of the factor influence on the traffic state of the road section when representing the instant condition of the road section represents the value extraction of the factors,SIMrepresents the minimum value of the correlation degree of the traffic condition at a certain time on a certain road section,
Figure GDA0002934759730000033
which represents the maximum value of the traffic condition correlation at a certain time on a certain road section.
Preferably, the travel time is:
Figure GDA0002934759730000034
wherein q isaRepresenting the traffic flow on the section a, CaRepresenting the actual capacity of the section a, ta 0Representing the free-run time, t, of the road sectiona(qa) Representing the time of travel, Z, actually through the road sectionaRepresenting the threshold value when the traffic is blocked, α and β are parameters of a commonly used BPR function model, and are usually taken as a ═ 0.15, β ═ 4.0, and ∈ > 0 is a constant;
when the road traffic is in a unblocked state, q is more than or equal to 0a≤Ca；
When the road traffic is in a crowded state, C is satisfieda＜qa＜Za；
When the road traffic is in a blocked state, Z is satisfieda≤qa≤Za+ε。
Due to the adoption of the technical scheme, the invention has the following advantages:
the invention provides a method for estimating a soft set of travel time, which aims at the problems of complexity of road traffic and uncertainty of the travel time, establishes various fuzzy rough sets based on the soft set, establishes a mapping relation from the traffic condition of a road section to one fuzzy rough set by considering main uncertainty factors influencing the traffic condition of the road, represents the traffic condition of the road section by using the fuzzy rough set, judges the traffic condition of the road section by using a matching function, and matches the corresponding calculation function of the travel time according to the determined traffic condition. The advantage of solving the uncertainty problem by using the soft set can be used for effectively estimating the uncertain travel time better, and the method is more suitable for the actual traffic condition.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
The invention provides a travel time calculation method based on a soft set, which comprises the following steps:
according to the actual condition of the road, the factors influencing the road traffic state mainly comprise: flow (flow is little, and flow is big), speed (slow, fast), time factor (general period, peak period, festival false peak), emergency (road construction, traffic fault, traffic control), environmental weather (fine, snow, fog, rain), like this, just can establish a factor set U:
u ═ flow, speed, ambient weather, incident, time factor }
And (3) solving the mutual relation among the factors to construct a fuzzy approximation space (U, R), wherein U represents a set composed of the factors influencing the travel time, and R represents the fuzzy relation among the elements in U.
And establishing a traffic condition data table of a certain road section according to the measured data or the simulation data of the certain road section. The road traffic state is obtained by predicting the provided traffic information of a certain section of road L, and the membership functions of all fuzzy sets can be obtained according to expert experience.
t＝{m1,m2,...,mn}
Wherein t represents an influencing factor in U, and m1,m2,...,mnRepresenting degrees of membership for n different cases of a factor, where miI ∈ (0, 1). For example, in terms of time factors, the time factor is a function table of degree of membership such asThe following steps of (1);
TABLE 1 time factor membership function Table
Time factor General period of time Peak hours Save false peak
Degree of membership 0.3 0.6 0.8
In this embodiment, the method of the present invention for obtaining R includes the following steps:
H(t)＝-∑μi(t)lgμi(t)
Figure GDA0002934759730000041
Figure GDA0002934759730000042
I(t,s)＝H(t)+H(s)-H(t,s)
t∈U,s∈U，μi(t) represents the degree of influence of the factor t on the travel time in the ith observation; n represents the total number of observations; h (t) represents the expectation of how much the factor t influences the travel time in these n observations. In other words, the overall degree of influence of the factor t on the travel time of the link in n observations is represented. When various factors are opposite to the stroke at the same timeThe influence between the two is not independent and mutually irrelevant; any two factors are considered to be unconnected in different observations, e.g., the flow factor at the ith and the speed factor at the jth are considered to be unrelated; mu as described abovei,j(t, s) indicate the degree of influence of the factors t and s on the travel time in the i-th and j-th observations, respectively. H (t, s) represents one expectation of the degree of influence of the factor t and the factor s on the travel time in n observations; i (t, s) is mutual information of the factors t and s, and reflects the numerical characteristics of the interrelation of the factors t and s, and the larger the value of the mutual information, the closer the two factors are in the influence degree on the travel time.
I (t, s) has the following properties:
nonnegativity, i.e., I (t, s) is not less than 0;
reciprocity, i.e., symmetry, I (t, s) ═ I (s, t);
I(t,t)＝H(t)。
mutual information has no special requirements on the distribution type of the variables, and the mutual information can describe not only linear correlation relations among the variables, but also nonlinear correlation relations among the variables. The mutual information has the defect of no normalization, and in order to compare the degree of dependence between different pairs of variables, the following formula is adopted to express the relationship R between two factors s and t in the domain of discourse U:
Figure GDA0002934759730000051
obviously, Rg(v,v)＝1,0≤Rg(v,q)≤1。
According to the formula
Figure GDA0002934759730000052
Wherein R isg(v,v)＝1,0≤Rg(v, q) ≦ 1, the fuzzy relation R on U may be found, and the fuzzy relation for the main factors of the road section L may be expressed as follows:
R(t,...,s)＝{R(t,t),R(s,s),...,R(t,s)}
the calculation of the above-described fuzzy relationship may be implemented by a computer program, where R (t, t) ≦ 1 indicates that the fuzzy relationship of the factor itself is 1, R (t, s) indicates a fuzzy relationship between any two factors in U, and 0 ≦ R (t, s) ≦ 1.
Step two, fuzzy rough set on fuzzy approximate space (U, R)
Figure GDA0002934759730000053
Representing the traffic condition of the road section, using the fuzzy set I on the U as the threshold set of the road condition of the road sectioniTo indicate a certain traffic state of the road section, e.g. clear, crowded, congested, etc., i.e. IiE { clear, crowded, blocked }, Ii＝(ωi1/t1,ωi2/t2,...,ωin/tn)。
The fuzzy rough set is then obtained by the following formula
Figure GDA0002934759730000054
Figure GDA0002934759730000055
Here, Ii(s) representing factor s in fuzzy set IiDegree of membership, e.g. Ii(t1)＝ωi1；
Figure GDA0002934759730000056
Representing factor t for traffic state IiThe minimum value of influence of (c); in a similar manner to that described above,
Figure GDA0002934759730000057
representing the traffic state I of the factor t for the road sectioniMaximum value of the resulting effect. Note the book
Figure GDA0002934759730000061
Threshold set I for congestioniAn expectation indicating the degree of influence of various factors on the traffic state when a certain congestion state occurs on the road section can be obtained by consulting related experts or by consulting related expertsThe history data of the link is obtained by arithmetic mean.
The fuzzy rough set of threshold values of the road traffic state is
Figure GDA0002934759730000062
There are three traffic states, namely clear, crowded, congested, for each factor in the set of influencing factors U there is a corresponding interval for the three traffic states.
And step three, constructing a soft fuzzy rough set.
Generally, a monitor describes traffic conditions on a road segment in terms of languages, such as: in general time periods, where traffic flow is low, speed is high, there are no emergencies, fog, etc., the observer actually gives an element x in the set E, which requires a mapping that converts the natural language vector into a fuzzy vector of U:
f:E→F(U),f(x)＝μ(x)
where E represents a set of language vectors provided by an observer, x ∈ E, and μ (x) represents a set of fuzzy vectors over U. Then find the form of its fuzzy rough set (q(t),
Figure GDA0002934759730000063
Figure GDA0002934759730000064
Figure GDA0002934759730000065
Thus, a soft fuzzy rough set is established, and by using the soft fuzzy rough set, the fuzzy rough set corresponding to the observed value x of the traffic condition of the road section at a certain moment can be obtained according to the digital characteristics of the road section at the certain moment provided by the observer.
An observer is set to describe a road section as 'peak in the morning and evening, large flow, slow speed, no emergency and no rain', and actually, the observer gives a parameter e ═{ morning and evening peak, large flow, slow speed, no, rain }, f (e) { 0.7/flow, 0/speed, 0.6/time factor, 0/emergency, 0.4/ambient weather }, therefore, a mapping f can be established, so that f (e) { 0.7/flow, 0. t/speed, 0.6/time factor, 0/emergency, 0.4/ambient weather }, thereby obtaining a fuzzy rough sugar set of the instant condition of the road section
Figure GDA0002934759730000066
Step four: using a matching function to find
Figure GDA0002934759730000067
And
Figure GDA0002934759730000068
then, according to the degree of correlation, the traffic state of the road section is judged.
Definition of correlation matching function:
Figure GDA0002934759730000071
wherein Q and Q are fuzzy rough sets of traffic conditions and instantaneous conditions of the road segments respectively,
Figure GDA0002934759730000072
representing factor t for traffic state IiThe minimum value of the influence of (a) is,q(t) represents the minimum value of the influence of the factor t on the traffic state of the road section when the road section is in the instant condition, and Λ represents the sum of the values;
Figure GDA0002934759730000073
representing the traffic state I of the factor t for the road sectioniThe maximum value of the influence that is produced,
Figure GDA0002934759730000074
the maximum value of the factor influence on the traffic state of the road section when representing the instant condition of the road section represents the value extraction of the factors,SIMexpress a certainThe minimum value of the traffic condition relevance at a certain time of the road section,
Figure GDA0002934759730000075
which represents the maximum value of the traffic condition correlation at a certain time on a certain road section.
Step five: and D, judging the traffic state of the road according to the correlation degree obtained by the correlation matching function in the step four, and then providing a corresponding travel time calculation formula.
According to the impedance function, the condition of the traffic state of the road is mapped to the travel time, and the three traffic states comprise: clear, congested, blocked, mapped to time, i.e., SIM → T.
When the road traffic of the road section is in a blocking state, the corresponding travel time calculation formula is as follows:
the travel time is calculated as follows:
Figure GDA0002934759730000076
wherein q isaRepresenting the traffic flow on the section a, CaRepresenting the actual capacity of the section a, ta 0Representing the free-run time, t, of the road sectiona(qa) Representing the time of travel, Z, actually through the road sectionaThe threshold value when the traffic is blocked is represented, alpha and beta are undetermined parameters of a commonly used BPR function model, alpha is 0.15, beta is 4.0, and epsilon is a constant value;
when the road traffic is in a unblocked state, q is more than or equal to 0a≤Ca；
When the road traffic is in a crowded state, C is satisfieda＜qa＜Za；
When the road traffic is in a blocked state, Z is satisfieda≤qa≤Za+ε。

Claims (4)

1. A travel time calculation method based on a soft set is characterized by comprising the following steps:
establishing a traffic condition data table of a certain road section, wherein the table mainly comprises speed, flow, environmental weather, emergencies and time factors; solving the mutual relation among all factors, and constructing a fuzzy approximation space (U, R), wherein U represents a set formed by all factors influencing travel time, and R represents the fuzzy relation among elements in U;
fuzzy rough set of space (U, R) by fuzzy approximation
Figure FDA0002934759720000011
A fuzzy set I on a set U representing the traffic condition of the road section and used for setting the threshold value of the road section with the road conditioniTo represent a certain traffic state of the road section and then to find a fuzzy rough set
Figure FDA0002934759720000012
Constructing a soft fuzzy rough set;
solving by correlation matching function
Figure FDA0002934759720000013
And
Figure FDA0002934759720000014
then, according to the size of the correlation SIM (Q, Q), the traffic state of the road section is judged; mapping to travel time according to the traffic state of the road;
the travel time is as follows:
Figure FDA0002934759720000015
wherein q isaRepresenting the traffic flow on the section a, CaRepresenting the actual capacity of the section a, ta 0Representing the free-run time, t, of the road sectiona(qa) Representing the time of travel, Z, actually through the road sectionaThe threshold value at the time of traffic jam is expressed, α, β are parameters of a commonly used BPR function model, and α is taken to be 0.15, β ═ 4.0, and ∈ > 0 is a constant;
when the road traffic is in a unblocked state, q is more than or equal to 0a≤Ca；
When the road traffic is in a crowded state, C is satisfieda＜qa＜Za；
When the road traffic is in a blocked state, Z is satisfieda≤qa≤Za+ε。
2. The method of claim 1, wherein the fuzzy rough set is used to calculate the travel time
Figure FDA0002934759720000016
Is composed of
Figure FDA0002934759720000017
Wherein
Figure FDA0002934759720000018
Representing factor t for traffic state IiThe minimum value of the influence of (a) is,
Figure FDA0002934759720000019
representing the traffic state I of the factor t for the road sectioniMaximum value of the effect produced;
Figure FDA00029347597200000110
Ii(s) representing factor s in fuzzy set IiR (t, s) represents the fuzzy relationship between any two factors in U;
threshold set I for congestioniAnd (3) an expectation of the degree of influence of various factors on the traffic state when a certain congestion state occurs on the road section.
3. The method of claim 1, wherein the travel time is calculated based on a soft setThe construction of the soft fuzzy rough set is as follows:
Figure FDA0002934759720000021
q(t) represents the minimum value of the influence of the factor t on the road section traffic state when the road section is in the instant condition;
Figure FDA0002934759720000028
the maximum value of the influence of the factor t on the road section traffic state when the road section is in the instant state is represented;
wherein
Figure FDA0002934759720000022
μ(s) represents the fuzzy vector set on U, R (t)iS) represents the fuzzy relationship between any two factors in U; and by using the soft fuzzy rough set, according to the digital characteristics of the road section at a certain moment provided by the observer, the fuzzy rough set corresponding to the traffic condition observation value x of the road section at a certain moment is obtained.
4. The method of claim 1, wherein the correlation matching function is:
Figure FDA0002934759720000023
wherein Q and Q are fuzzy rough sets of traffic conditions and instantaneous conditions of the road segments respectively,
Figure FDA0002934759720000024
representing factor t for traffic state IiThe minimum value of the influence of (a) is,q(t) represents the minimum value of the influence of the factor t on the traffic state of the road section when the road section is in the instant condition, and Λ represents the sum of the values;
Figure FDA0002934759720000025
representing the traffic state I of the factor t for the road sectioniThe maximum value of the influence that is produced,
Figure FDA0002934759720000026
the maximum value of the factor influence on the traffic state of the road section when representing the instant condition of the road section represents the value extraction of the factors,SIMrepresents the minimum value of the correlation degree of the traffic condition at a certain time on a certain road section,
Figure FDA0002934759720000027
which represents the maximum value of the traffic condition correlation at a certain time on a certain road section.
CN201810847570.2A 2018-07-27 2018-07-27 Travel time calculation method based on soft set Active CN108922191B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810847570.2A CN108922191B (en) 2018-07-27 2018-07-27 Travel time calculation method based on soft set

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810847570.2A CN108922191B (en) 2018-07-27 2018-07-27 Travel time calculation method based on soft set

Publications (2)

Publication Number Publication Date
CN108922191A CN108922191A (en) 2018-11-30
CN108922191B true CN108922191B (en) 2021-05-04

Family

ID=64418982

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810847570.2A Active CN108922191B (en) 2018-07-27 2018-07-27 Travel time calculation method based on soft set

Country Status (1)

Country Link
CN (1) CN108922191B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6324101B2 (en) * 2014-02-21 2018-05-16 株式会社ゼンリン TRAVEL TIME DATA PREPARATION DEVICE, TRAVEL TIME DATA PREPARATION METHOD, AND PROGRAM
CN109712402B (en) * 2019-02-12 2021-11-12 南京邮电大学 Mobile object running time prediction method and device based on meta-path congestion mode mining

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477746B (en) * 2009-01-05 2010-06-02 东南大学 Circuit simulation device for uni-direction road grid traffic flow distribution
CN102110365B (en) * 2009-12-28 2013-11-06 日电（中国）有限公司 Road condition prediction method and road condition prediction system based on space-time relationship
CN106960572B (en) * 2017-04-05 2019-04-23 大连交通大学 A kind of motorway journeys time reliability calculation method based on delay time coefficient

Also Published As

Publication number Publication date
CN108922191A (en) 2018-11-30

Similar Documents

Publication Publication Date Title
CN108304668B (en) Flood prediction method combining hydrologic process data and historical prior data
Castro-Neto et al. AADT prediction using support vector regression with data-dependent parameters
Talei et al. Runoff forecasting using a Takagi–Sugeno neuro-fuzzy model with online learning
WO2020248228A1 (en) Computing node load prediction method in a hadoop platform
CN109242265B (en) Urban water demand combined prediction method based on least square sum of errors
CN114254561A (en) Waterlogging prediction method, waterlogging prediction system and storage medium
Danladi et al. Assessing the influence of weather parameters on rainfall to forecast river discharge based on short-term
CN108922191B (en) Travel time calculation method based on soft set
CN109544926B (en) Traffic flow restoration method based on intersection correlation
CN112270355A (en) Active safety prediction method based on big data technology and SAE-GRU
CN116739376A (en) Highway pavement preventive maintenance decision method based on data mining
CN110807601A (en) Park road deterioration analysis method based on truncation data
Zhou et al. Prediction and early warning method of inundation process at waterlogging points based on Bayesian model average and data-driven
CN113536665B (en) Road surface temperature short-term prediction method and system based on characteristic engineering and LSTM
Coppola Jr et al. Fuzzy rule-based methodology for estimating monthly groundwater recharge in a temperate watershed
CN110490365B (en) Method for predicting network car booking order quantity based on multi-source data fusion
CN111598328A (en) Power load prediction method considering epidemic situation events
He et al. An Improved Coupling Model of Grey-System and Multivariate Linear Regression for Water Consumption Forecasting.
CN115792853A (en) Radar echo extrapolation method based on dynamic weight loss
Galanis et al. Weather-based road condition estimation in the era of Internet-of-Vehicles (IoV)
Enright et al. A Bayesian approach for estimating characteristic bridge traffic load effects
Rassafi et al. Predicting urban trip generation using a fuzzy expert system
Jiang et al. Predicting the pavement performance: A comparison on traditional and multivariate time series model
CN117831287B (en) Method, device, equipment and storage medium for determining highway congestion index
Baykal et al. Accident Severity Prediction in Big Data Using Auto-Machine Learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant